Alex Carlier @alexcarliera Twitter profile

Pinned Tweet

Alex Carlier

8 months

Another experiment with Gaussian Painters ✨🎨 By optimizing 3D Gaussian Splattings over separate images at several viewpoints, it is possible to get a Steganography effect! Three paintings are hidden in those gaussian splats

Alex Carlier

@alexcarliera

8 months

I optimized 3D Gaussian Splattings over a single picture on a 2D plane. I'm calling this "Gaussian Painters" 🎨✨ Watch the gaussian splats work to paint the Girl with a Pearl Earring! Here's how I did it (code below) ⬇️⬇️

12

74

645

21

224

1K

Last Seen Profiles

@sarameikasai

@RadfemBlack

@TyWilson44

@booksss_da

@sugatasaek78451

@itskaiwan

@TasKing1

@SELDNSpaz

@treporapat

@cnn_co_jp

@sissybabyella

@Lone_Star_Heat

@drunkhys

@morellifit

@circo_voador

@KETAMINE____

@bitcoin_chronic

@rusherton

@hockey_east

@RyouonRitsu

@LopezSanusi

@harufnbr_

@klmatmnnoor

@YShiblog

@miuskmt_staff

@MichaScibe21823

@g66306

@the_gigi_era

@rr___xq

@anahitairani1

@KaitlynnAn32743

@rishi_chan91792

@joaokeef

@AGTheOrg

@ig_uzm

@Web3WomenCommun

Alex Carlier

@alexcarliera

5 months

Upscale-A-Video was just released and it's so good! 🤯 It's a temporal-consistent Diffusion Model for video Super-Resolution, and has some of the best results I've ever seen, look at how sharp those lines become! More details below ⬇️⬇️

43

280

2K

Alex Carlier

@alexcarliera

5 months

Google just revealed an ABSOLUTE depth estimation model 🤯 As opposed to recent depth models (Marigold, PatchFusion) which aim for maximum details, DMD aims to estimate the ABSOLUTE depth (in meters) within the image More details below ⬇️⬇️

27

270

2K

Alex Carlier

@alexcarliera

5 months

Meta AI strikes again, with Relightable Gaussian Codec Avatars This is an update to the Meta Codec Avatars 2.0, building on 3D Gaussian Splatting. As a result, we get fully relightable real-time avatars, accurate at the hair strand level 🤯 More details below ⬇️⬇️

45

368

2K

Alex Carlier

@alexcarliera

8 months

Gaussian Painters imported into #b3d as ellipsoids (3D Gaussian Splatting plugin for Blender - work in progress)

41

220

2K

Alex Carlier

@alexcarliera

5 months

Wow Marigold 🌼 depth estimation works extremely well! 🤯 And the best thing is that the checkpoints and code are fully available for commercial use! Try it out yourself! ⬇️⬇️

17

179

1K

Alex Carlier

@alexcarliera

4 months

This is literally magic 🤯 FMA-Net is a new AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️

59

153

1K

Alex Carlier

@alexcarliera

5 months

PatchFusion was just released. Compared to ZoeDepth, it predicts depth maps with much finer details, just look at the comparison below! 🤯 Its main contribution is a new Global-to-Local module and Consistency-Aware Training. More examples below (with code) ⬇️⬇️

22

137

899

Alex Carlier

@alexcarliera

5 months

LooseControl was just released and it's so good! 🔥 It enables depth-map conditioned image generation, but unlike ControlNet, the 3D boxes enable less strict control with simple bounding boxes. And look at how stable it is across frames! More examples (with code) below ⬇️⬇️

22

120

798

Alex Carlier

@alexcarliera

4 months

This scene was scanned using only 3 pictures 🤯 In my opinion, this was the biggest flaw of NeRFs & 3D Gaussian splats: they are trained from scratch every time with no knowledge of the world. With ReconFusion, we now acquire it from diffusion models More examples below ⬇️⬇️

18

117

758

Alex Carlier

@alexcarliera

10 months

Having accurate keypoints is extremely important for many tasks in AI and 3D. Here I trained a reenactment network with @reshotAI keypoints!

16

138

742

Alex Carlier

@alexcarliera

7 months

New 3D Gaussian Splatting recording! Those metallic reflections and leather were captured REALLY well! When looking closer, you can also see how the watch hands are modeled with just a couple of elongated gaussians. #GaussianSplatting

19

70

751

Alex Carlier

@alexcarliera

5 months

This scene was scanned using only 3 pictures 🤯 In my opinion, this was the biggest flaw of NeRFs & 3D Gaussian splats: they are trained from scratch every time with no knowledge of the world. With ReconFusion, we now acquire it from diffusion models More examples below ⬇️⬇️

27

90

708

Alex Carlier

@alexcarliera

4 months

SUPIR: Scaling Up to Excellence. Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild 🔥 Links below ⬇️⬇️

23

79

676

Alex Carlier

@alexcarliera

3 years

Made a little visualisation for my latest project on free-view one-shot image generation 🤩 Just pick a photo, and generate images with full control of rotation and facial expressions. Or choose a driving video and let the magic happen✨ @ylecun Try it for free using @litso_app !

18

111

650

Alex Carlier

@alexcarliera

9 months

I have written a tutorial on how to train your own "3D Gaussian Splatting" models! #GaussianSplatting Write me here if you're facing any issues. ⬇️⬇️

23

95

652

Alex Carlier

@alexcarliera

8 months

I optimized 3D Gaussian Splattings over a single picture on a 2D plane. I'm calling this "Gaussian Painters" 🎨✨ Watch the gaussian splats work to paint the Girl with a Pearl Earring! Here's how I did it (code below) ⬇️⬇️

12

74

645

Alex Carlier

@alexcarliera

4 months

OpenVoice was just released! 🤯 Given a short audio clip, it clones the reference voice and can generate speech in multiple languages, while having control over emotion, accent, rhythm, pauses, and intonation! Code & details below ⬇️⬇️

13

125

627

Alex Carlier

@alexcarliera

4 months

A new highly accurate OCR was just released and it's open-source! Surya is accurate to the line-level, and multilingual. Well, in this example, only the newspaper name was not detected 😅 Link below ⬇️⬇️

12

77

517

Alex Carlier

@alexcarliera

5 months

EfficientSAM was just released and it's fast! 💨 With 20x fewer params, it is now 20x faster than the original SAM segmentation model, while staying in the same accuracy range. See below for the project page and an interactive @huggingface space to try it out! ⬇️⬇️

14

111

496

Alex Carlier

@alexcarliera

10 months

Mediapipe vs my in-house keypoint detector for Reshot AI!

13

50

455

Alex Carlier

@alexcarliera

8 months

New 3D Gaussian Splatting capture at the Vintage Cars association in Versailles, from a 30 seconds recording. Some floaters were cleaned with my b3d plugin. Original output below ⬇️⬇️ #GaussianSplatting

13

40

456

Alex Carlier

@alexcarliera

8 months

Imagine this on the @Nike website. This is a 3D capture of the Nike ZoomX Vaporfly Next%, and visualizing this feels as real as touching the real shoe. 3D Gaussian Splattings are SO good at modeling fine structures, like in this case the transparent fabric. #GaussianSplatting

14

38

442

Alex Carlier

@alexcarliera

5 months

Copy-paste any object into an image with AI! 🤯 Here's one application of using AnyDoor for virtual try-on, but it's much more general and is designed to maintain texture details yet allow versatile local variations! Links below (with code!) ⬇️⬇️

9

89

427

Alex Carlier

@alexcarliera

4 months

Get crisp 3D Gaussian splats from blurry inputs 🤯 Capturing sharp videos is often impossible because of lens defocusing, object motion or camera shake. And 3DGS learns to fit this. "Deblurring 3DGS" optimizes a small MLP to model the scene blurriness! More details below ⬇️⬇️

8

75

432

Alex Carlier

@alexcarliera

4 months

An open-source version of AnimateAnyone was just released! (Moore-AnimateAnyone) I just tried it, the quality is not there just yet, but it has great potential! Links below ⬇️⬇️

3

68

425

Alex Carlier

@alexcarliera

7 months

3.8 mb 🤯 I tried the 3D Gaussian Splatting add-on for Unity by @aras_p on my Nike shoe capture, and when using the “Very low” quality, the file size becomes 3.8mb with minimal visual loss. That’s the lowest file size I’ve seen for a 3DGS yet! #GaussianSplatting

18

45

423

Alex Carlier

@alexcarliera

5 months

Wow, generate infinite videos from a single image 🤯 WonderJourney creates coherently connected 3D scenes along a controllable camera trajectory. Look how running the code three times results in completely different videos! More examples below ⬇️⬇️

14

60

401

Alex Carlier

@alexcarliera

5 months

While everyone is waiting for AnimateAnyone, MagicAnimate was just released and it's really impressive! 🤯 It needs a single image and a motion video, and it produces an animated video! See below for more examples ⬇️⬇️

8

75

379

Alex Carlier

@alexcarliera

5 months

A new video generation paper just dropped 🤯 DreaMoving creates human dance videos given a target identity and posture sequences. But unlike AnimateAnyone and MagicAnimate, a full body picture is not required as input (only face + optional prompt). More details below ⬇️⬇️

19

88

375

Alex Carlier

@alexcarliera

5 months

So Impressive 🤯 StreamDiffusion, built on sd-turbo, can generate up to 150 images per second. Hardware configuration below ⬇️⬇️

14

47

374

Alex Carlier

@alexcarliera

8 months

How do 3D Gaussian Splatting models handle view-dependency? Using Spherical Harmonics Here's how it works ⬇️⬇️ #GaussianSplatting

11

54

361

Alex Carlier

@alexcarliera

8 months

Using Gaussian Painters, you can also create a psychedelic illusion using two orthogonal images!

Alex Carlier

@alexcarliera

8 months

I optimized 3D Gaussian Splattings over a single picture on a 2D plane. I'm calling this "Gaussian Painters" 🎨✨ Watch the gaussian splats work to paint the Girl with a Pearl Earring! Here's how I did it (code below) ⬇️⬇️

12

74

645

8

40

357

Alex Carlier

@alexcarliera

4 months

A new real-time Radiance Field paper beating 3DGS was just released! 🔥 Similarly to 3D Gaussian Splatting, TRIPS optimizes a point-cloud with color, position & size that gets splatted to the screen. But it does so using a single trilinear write in an image pyramid More info ⬇️

10

59

352

Alex Carlier

@alexcarliera

5 months

Adaptive Shells was just awarded best paper at SIGGRAPH Asia! 🙌 It's a new hybrid method between a NeRF and mesh, and achieves up to 300 FPS at HD resolution! More details below ⬇️⬇️

5

44

337

Alex Carlier

@alexcarliera

5 months

DreamBooth from a SINGLE image with perfect accuracy 🤯 Unlike specialized models like AnimateAnyone, DreamTuner is a general method for subject-driven generation, controllable via text or pose But it works so well, it can create temporally consistent animations! More below ⬇️

10

56

333

Alex Carlier

@alexcarliera

5 months

Gaussian Head Avatars look amazing! 🤯 Capture a dynamic 3D Gaussian splat of a face, then animate it in 3D using another actor. Imagine the potential for the film industry! More examples below ⬇️⬇️

8

50

332

Alex Carlier

@alexcarliera

5 months

Google just announces VideoPoet: a multimodal video generation model! It's massively multimodal and can take as input: text, image, depth & optical flow or a masked video and is one of the first models that generates video + audio! More info below ⬇️⬇️

9

68

319

Alex Carlier

@alexcarliera

5 months

Meta AI's new real-time translation model is so impressive! 🤯 It streams the translation BEFORE waiting for the end of a sentence, with <2 seconds of latency. See how fast the translation appears after the speaker starts talking 💨 More details below (with code!) ⬇️⬇️

11

61

320

Alex Carlier

@alexcarliera

5 months

Wow this is cool! 🤯 PixelLLM generates image captions with pixel coordinates Just a few years ago, the field of Explainable AI was amazed by simple heatmaps in the image classification task (single label prediction) This brings it to a whole new level! Project links below ⬇️

8

75

314

Alex Carlier

@alexcarliera

5 months

Wow! 🤯🔥 Beyond First-Order Tweedie: Solving Inverse Problems using Latent Diffusion Links below ⬇️⬇️

7

47

308

Alex Carlier

@alexcarliera

9 months

3D Gaussian Splatting is INSANELY good at fur rendering. Look at the fuzzy details here! Makes sense since it literally optimizes over small ellipsoid particles, as opposed to NeRF or photogrammetry. #GaussianSplatting

9

40

299

Alex Carlier

@alexcarliera

4 months

Deblurring 3D Gaussian Splatting is seriously amazing! 🔥 Can't wait to try it out on my captures!

Alex Carlier

@alexcarliera

4 months

Get crisp 3D Gaussian splats from blurry inputs 🤯 Capturing sharp videos is often impossible because of lens defocusing, object motion or camera shake. And 3DGS learns to fit this. "Deblurring 3DGS" optimizes a small MLP to model the scene blurriness! More details below ⬇️⬇️

8

75

432

3

29

298

Alex Carlier

@alexcarliera

10 months

Mediapipe vs @reshotAI keypoints!

11

42

275

Alex Carlier

@alexcarliera

5 months

Segment Anything Model (SAM) now runs at 30 FPS on an iPhone! 🤯 EdgeSAM is the first SAM variant that can run at over 30 FPS on an iPhone 14 with good quality. Low how accurately it segments tiny vegetables! Code and @HuggingFace demo below! ⬇️⬇️

3

57

273

Alex Carlier

@alexcarliera

4 months

3D Gaussian Splattings from a single image 🤯 Compared to recent novel-view synthesis approaches (like Stable Zero123) which generate novel views as images (causing inconsistencies) this work generates 3D Gaussians directly (via a pointcloud and triplane features) More below ⬇️

7

44

256

Alex Carlier

@alexcarliera

5 months

The first Consistency Model for Video was just released! 🤯 It enables video generation with as little as 4 sampling steps: generating 16 frames (at 256x256 resolution) takes 10 seconds only! So not real-time yet (as for images), but close! More details below! ⬇️⬇️

7

39

253

Alex Carlier

@alexcarliera

5 months

Wow this is cool! SMERF is a streamable NeRF that runs in real-time on any device with the quality of Zip-NeRF! Try it yourself! ⬇️⬇️

9

18

244

Alex Carlier

@alexcarliera

4 months

The code for DreamTalk was just released! Given any audio (text or song) and a single image frame, it generates a lip-synced animated video, copying the "expression" of a style reference. Links below ⬇️⬇️

5

49

242

Alex Carlier

@alexcarliera

10 months

Mediapipe vs @reshotAI keypoints. The interpolations are so satisfying!

12

29

241

Alex Carlier

@alexcarliera

4 months

A comparison between 3D Gaussian Splatting and the new TRIPS radiance field rendering method ⬇️ Can't wait to try this out on some of my scenes! 🔥

Alex Carlier

@alexcarliera

4 months

A new real-time Radiance Field paper beating 3DGS was just released! 🔥 Similarly to 3D Gaussian Splatting, TRIPS optimizes a point-cloud with color, position & size that gets splatted to the screen. But it does so using a single trilinear write in an image pyramid More info ⬇️

10

59

352

6

24

237

Alex Carlier

@alexcarliera

4 months

This new video upscaling & deblurring method (FMA-Net) works insanely well! ⬇️

Alex Carlier

@alexcarliera

4 months

This is literally magic 🤯 FMA-Net is a new AI method for video deblurring! It uses complex motion representation learning for spatio-temporally-variant restoration with kernels that are aware of motion trajectories. More info below ⬇️⬇️

59

153

1K

2

43

233

Alex Carlier

@alexcarliera

4 months

Temporally stable 3D body MoCap with a SINGLE camera & occlusions!🔥 Obtaining globally coherent & plausible motions through occlusions is an incredibly difficult problem, but RoHM (by Meta and ETH Zurich) seems to have just solved this! More info below ⬇️⬇️

9

37

227

Alex Carlier

@alexcarliera

5 months

ControlNet with higher fidelity, faster training & lower GPU memory 🔥 SCEdit introduces a lightweight tuning module called SC-Tuner Project links below ⬇️⬇️

4

39

226

Alex Carlier

@alexcarliera

5 months

Photopea just announced their new Background Removal tool It's available for FREE and works imo better than "Remove bg"! Wow 🤯 More examples below ⬇️⬇️

8

24

215

Alex Carlier

@alexcarliera

7 months

Wow the loading of #GaussianSplatting in @LumaLabsAI is so smart and satisfying! 😍 Only show the point cloud till fully loaded + progressive streaming from center to background

2

22

216

Alex Carlier

@alexcarliera

4 months

Just tried @LumaLabsAI 's Text-to-3D (low-poly) 3D generation is now as fast as image generation, which you can then upscale for higher resolution 3D models. Looks promising! 🔥

Luma AI

@LumaLabsAI

4 months

🔥 Introducing Genie 1.0, our first step towards building multimodal AI. Genie is a text-to-3d model capable of creating any 3d object you can dream of in under 10 seconds with materials, quad mesh retopology, variable polycount, and in all standard formats! Try it on web and in…

107

509

3K

2

37

213

Alex Carlier

@alexcarliera

8 months

This is insane! @antimatter15 has implemented a WebGL viewer for 3D Gaussian Splattings. Unlike other implementations, this uses vanilla WebGL, and runs on any device in the browser (60+ FPS on my desktop, 30 FPS on mobile but no touch controls yet). Link to try it below ⬇️⬇️

Alex Carlier

@alexcarliera

8 months

Imagine this on the @Nike website. This is a 3D capture of the Nike ZoomX Vaporfly Next%, and visualizing this feels as real as touching the real shoe. 3D Gaussian Splattings are SO good at modeling fine structures, like in this case the transparent fabric. #GaussianSplatting

14

38

442

2

36

216

Alex Carlier

@alexcarliera

8 months

I created an upside-down optical illusion using Stable Diffusion XL ✨✨ Here's how I did it ⬇️⬇️ #SDXL

11

38

210

Alex Carlier

@alexcarliera

4 months

Try furniture in your living room before buying 🔥 Amazon just announced "Diffuse to Choose", a new diffusion-based image-conditioned inpainting model. It is fast and accurately copies fine details of the reference to the target image. More examples below ⬇️⬇️

8

39

208

Alex Carlier

@alexcarliera

5 months

High quality real-time NeRFs on your phone🤯 MERF is a new streamable memory-efficient approach that achieves real-time performance while equaling the quality of Zip-NeRF (and outperforming 3DGS) Try it out yourself below ⬇️⬇️

5

28

207

Alex Carlier

@alexcarliera

5 months

We made a small promo video for our upcoming #LEGO AR app! What do you think? ❤️ Join the waitlist ⬇️⬇️

21

204

Alex Carlier

@alexcarliera

5 months

This is so perfect 🔥✨ SDXL Auto FaceSwap by @fffiloni enables to create new images using the face of a source image. Try it out in this @huggingface space ⬇️⬇️

5

31

200

Alex Carlier

@alexcarliera

4 months

Reminds of LooseControl, but for video! Controlling 3d cubes in a video would be 🔥!

Alex Carlier

@alexcarliera

4 months

Fully control AI videos with simple boxes 🤯 Recent approaches enable control with human pose or depth maps, but creating these maps is challenging. TrailBlazer (built on top of ZeroScope) enables control with boxes through spatial & temporal attention map editing More below ⬇️

1

7

79

1

20

183

Alex Carlier

@alexcarliera

5 months

#GaussianSplatting from just two images in a single forward pass 🤯 PixelSplat predicts a dense probability distribution and samples Gaussians through a differentiable operation allowing to back-propagate gradients to the 3DGS representation Completely insane results! More ⬇️⬇️

3

28

185

Alex Carlier

@alexcarliera

4 months

Tested Meta AI's new Audio2Photoreal: photorealistic animated 3D Codec Avatars from audio alone, sound on 🔊 Needs better face expressions, but very promising multi-view results! Code links below ⬇️⬇️

9

33

183

Alex Carlier

@alexcarliera

8 months

New 3D Gaussian Splatting capture of a park near Versailles. The hardest part in shooting outdoors is to find the perfect timing when no people are seen 😅 #GaussianSplatting

7

18

182

Alex Carlier

@alexcarliera

4 months

Neural radiance field methods like Zip-NeRF perform very poorly when given only a few images. This is because they learn the scene from scratch with no prior information about the world. ReconFusion fixes that! 🔥⬇️⬇️

Alex Carlier

@alexcarliera

4 months

This scene was scanned using only 3 pictures 🤯 In my opinion, this was the biggest flaw of NeRFs & 3D Gaussian splats: they are trained from scratch every time with no knowledge of the world. With ReconFusion, we now acquire it from diffusion models More examples below ⬇️⬇️

18

117

758

2

27

177

Alex Carlier

@alexcarliera

4 months

DepthAnything was just released! 🔥 TLDR: it was trained on labeled + 62M unlabeled images The encoder is initialized with DINOv2, a segmentation models helps to detect the sky (and set depth to ∞), the unlabeled images are strongly distorted (color, blur, CutMix). More ⬇️⬇️

2

19

158

Alex Carlier

@alexcarliera

5 months

Get in-context descriptions of any object in an image 🤯 Osprey is a new Pixel Understanding model that can be integrated with Segment Anything Model (SAM) to obtain multi-granularity semantics of any region in an image! More info below ⬇️⬇️

4

30

153

Alex Carlier

@alexcarliera

8 months

I optimized the Spherical Harmonic coefficients of a grid of 100x100 gaussian spheres to fit pictures at different viewpoints, creating a lenticular card effect! ✨🌈 Once trained, the images are stored in the SH coefficients of SHARED spheres Here's how it works (w. code) ⬇️⬇️

3

17

141

Alex Carlier

@alexcarliera

5 months

Generate high-resolution UV textures from just a mesh 🤯 Compared to other approaches, Paint3D achieves to create UV textures without embedded illumination information. It does so using a novel coarse-to-fine approach. More info below ⬇️⬇️

2

26

143

Alex Carlier

@alexcarliera

5 months

Generate a 3D object from a few pictures only! 🤯 UpFusion also works taking a single picture as input, but providing a few UNPOSED images improves the fidelity to the input object! More details below ⬇️⬇️

3

21

130

Alex Carlier

@alexcarliera

9 months

Font resolution test on a 3D Gaussian Splatting capture. High frequency areas use more splats, while uniform ones are covered by just a handful of gaussians. Still mind blown that this uses only 3D ellipsoids. #GaussianSplatting

5

14

125

Alex Carlier

@alexcarliera

5 months

Another video showing Relightable Gaussian Codec Avatars in more details

2

13

127

Alex Carlier

@alexcarliera

5 months

Ok this is cool! 🤯 Testing the @krea_ai AI Enhancer on one of our BricksAR #LEGO buildings to turn it into a realistic Parisian café 😍 Check below for more ⬇️⬇️ @Scobleizer

10

20

123

Alex Carlier

@alexcarliera

8 months

And here you go! A 3D Gaussian Splatting running in real-time in the browser on a 3-year old iPhone Try it out here ⬇️⬇️

Kevin Kwok

@antimatter15

8 months

@alexcarliera I just updated the camera controls and implemented touch controls on mobile!

3

0

10

11

13

119

Alex Carlier

@alexcarliera

4 years

Excited to announce that "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation" has been accepted to #NeurIPS ! If you're interested in vector graphics & sketch generation, feel free to check it out Code: Paper:

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation

Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions. However, despite the success of deep learning-based models applied to...

arxiv.org

hardmaru

@hardmaru

4 years

DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation Exciting work from @alxandrecarlier et al. Transformer-based hierarchical generative models learn latent representations of vector graphics, with nice applications in SVG animation.

7

64

291

2

34

118

Alex Carlier

@alexcarliera

10 months

Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction Paper page: Generating realistic human 3D reconstructions using image or video data is essential for various communication and entertainment applications. While existing methods achieved…

3

18

117

Alex Carlier

@alexcarliera

9 months

Tested 3D Gaussian Splatting on a capture from the Comics Art Museum, Brussels. 🇧🇪 Super impressive training convergence and real-time rendering! #GaussianSplatting

5

15

117

Alex Carlier

@alexcarliera

5 months

Ok this is wild for 3D artists. What if you could just get a ready-to-use material by simply clicking on a material in an IMAGE? This is what MaterialPalette solves. Especially useful when modeling from a reference image, just pick the correct material! Project page below ⬇️⬇️

5

16

113

Alex Carlier

@alexcarliera

8 months

There's something beautiful about visualizing impressionist artworks from Claude Monet using new technology. Peaceful scenes from the past that become 3d dreams, and which would be fun to play with in VR. Created using GaussianPainters. #GaussianSplatting

4

16

109

Alex Carlier

@alexcarliera

5 months

For reference, here is the ground truth depth maps for the previous images. DMD improves the relative depth error by up to 25% over ZoeDepth! One finding is that conditioning on the FOV is essential for disambiguating depth-scale.

4

8

108

Alex Carlier

@alexcarliera

4 months

3D Gaussian Splatting vs TRIPS (new radiance field method running at 60 FPS 🔥) ⬇️⬇️

Alex Carlier

@alexcarliera

4 months

A new real-time Radiance Field paper beating 3DGS was just released! 🔥 Similarly to 3D Gaussian Splatting, TRIPS optimizes a point-cloud with color, position & size that gets splatted to the screen. But it does so using a single trilinear write in an image pyramid More info ⬇️

10

59

352

1

12

102

Alex Carlier

@alexcarliera

5 months

I tested the ControlNet for video (MagicAnimate) and here are is my opinion: it works great but has some flaws. - the identity of the motion video leaks to the resulting video (and deforms body shape) - bad hands and face (unsurprisingly!) But a great first step for consistent…

Alex Carlier

@alexcarliera

5 months

While everyone is waiting for AnimateAnyone, MagicAnimate was just released and it's really impressive! 🤯 It needs a single image and a motion video, and it produces an animated video! See below for more examples ⬇️⬇️

8

75

379

7

16

93

Alex Carlier

@alexcarliera

9 months

New 3D Gaussian Splatting capture of an amethyst. Look at those reflections 😍 #GaussianSplatting

6

90

Alex Carlier

@alexcarliera

8 months

Forget spirals, I just invented AI emojis 👀

13

12

88

Alex Carlier

@alexcarliera

5 months

Those fonts do not exist 🤯 @AdobeResearch strikes again with VecFusion, a new diffusion approach for Vector Image generation. Here it generates missing glyphs from just a few examples! If you follow me from my DeepSVG paper you know how excited I'm about this! More below ⬇️⬇️

3

9

87

Alex Carlier

@alexcarliera

8 months

Create your own upside-down optical illusions with Stable Diffusion XL! 🎨✨ I have created a colab notebook with the modified diffusion process for you to try! Link in the comments ⬇️⬇️

10

20

84

Alex Carlier

@alexcarliera

4 months

Project page: arXiv: Code (soon): Follow @alexcarliera for more content on AI!

GitHub - KAIST-VICLab/FMA-Net: [CVPR 2024, Oral 0.78%] Official repository of FMA-Net

[CVPR 2024, Oral 0.78%] Official repository of FMA-Net - KAIST-VICLab/FMA-Net

github.com

3

13

86

Alex Carlier

@alexcarliera

4 months

Project page: arXiv: @HuggingFace page (give it an upvote!):

Paper page - Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restora...

huggingface.co

2

8

82

Alex Carlier

@alexcarliera

8 months

@Wizard_Mahi07 @MKBHD Options for more storage (6TB and 12 TB)

8

2

78

Alex Carlier

@alexcarliera

10 months

These cheeks/wrinkles do not exist! The @reshotAI reenactment network only takes the keypoints as input

4

10

79

Alex Carlier

@alexcarliera

5 months

Get prepared for more spambots in the coming months 🤯 @elonmusk Tencent just announced AppAgent, an LLM-based multimodal agent framework designed to control phone apps This looks helpful for the visually impaired, but can also make bots much easier to deploy More info ⬇️⬇️

2

19

76

Alex Carlier

@alexcarliera

8 months

The only way current LLMs can "reason" is through their own outputs. This is why prompts such as "Let's think step by step" can help in case of complicated logical requests. What OpenAI is probably working on for GPT-5 is an "internal thoughts" stream (that doesn't get printed…

Tim Kietzmann

@TimKietzmann

8 months

Well, actually, yes.

513

7K

153K

6

8

81

Alex Carlier

@alexcarliera

8 months

And here's the code:

GitHub - ReshotAI/gaussian-painters: Gaussian Painters using 3D Gaussian Splatting

Gaussian Painters using 3D Gaussian Splatting. Contribute to ReshotAI/gaussian-painters development by creating an account on GitHub.

github.com

0

7

80

Alex Carlier

@alexcarliera

4 months

Fully control AI videos with simple boxes 🤯 Recent approaches enable control with human pose or depth maps, but creating these maps is challenging. TrailBlazer (built on top of ZeroScope) enables control with boxes through spatial & temporal attention map editing More below ⬇️

1

7

79